Server Quality Checklist

Tool Scores

• pexels_curated_photosA
  4.2/5.0
  Behavior4/5

  Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

  Annotations already declare readOnlyHint=true, so the description's 'Read-only' is redundant but reinforces safety. However, it adds valuable behavioral context: the hourly refresh, pagination, and the URL structure guidance ('pick the closest fit rather than always using original'). No contradictions.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is two sentences with zero fluff. The first sentence states the core function, and the second sentence provides a concise, actionable detail about URL sizes. Every word earns its place.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness4/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  For a simple list tool with no output schema, the description covers return values ('compact photo objects'), pagination, refresh rate, and provides useful details about the `src` object. It lacks only minor aspects like error handling or rate limits, but these are not critical for such a straightforward tool.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema description coverage is 100%, with both parameters (page, per_page) clearly described. The description adds no new parameter-specific semantics beyond mentioning pagination, which is already implied by the schema and parameter names. Baseline 3 is appropriate.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states the tool's purpose with a specific verb ('List'), resource ('Pexels' hand-curated photo picks'), and adds distinctive details ('refreshed hourly', 'paginated'). This differentiates it from sibling tools like pexels_search_photos and pexels_get_photo by emphasizing the 'curated' nature.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines4/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description gives clear context for when to use the tool (when you want curated content, not search results), though it doesn't explicitly name alternatives or exclusions. The note about picking the closest URL size is a practical usage guideline for the output.

  Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

• pexels_search_photosA
  4.2/5.0
  Behavior4/5

  Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

  Annotations include readOnlyHint=true, and the description reinforces 'Read-only'. It adds valuable behavior beyond annotations: returns pre-sized URLs with specific size options, mentions courtesy credit/license terms, and advises picking the closest fit rather than always using 'original'. This enriches the agent's understanding of response behavior.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is concise and front-loaded: first sentence states the core purpose, second explains return format and licensing, third gives specific usage guidance on URL selection. Every sentence earns its place, with no fluff or repetition.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness4/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  Given no output schema, the description sufficiently explains return values (compact photo objects with pre-sized URLs and credit). It covers key usage guidance and licensing. It does not mention pagination metadata or total result counts, but the schema describes page/per_page, so the agent can infer. This is nearly complete for a search tool.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema coverage is 100%, so the baseline is 3. The description mentions the optional filters (orientation/size/color/locale) but does not add semantic detail beyond the schema's own parameter descriptions. It does not clarify parameter usage beyond grouping them as filters.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states the tool's purpose: 'Search Pexels for photos matching a query' with specific verb and resource. It distinguishes from siblings by emphasizing query-based search vs. curated photos or single photo retrieval, and lists optional filters.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines4/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description establishes clear context: use this tool to search photos by query with optional filters. It does not explicitly mention alternatives or when-not-to-use, but the context is sufficiently clear for an agent to select it for search tasks.

  Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

• pexels_get_photoA
  4.3/5.0
  Behavior4/5

  Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

  Annotations already provide readOnlyHint and openWorldHint, but the description adds value by disclosing the response structure (src field with named pre-sized URLs) and offering guidance on choosing the closest fit. This goes beyond the annotations and gives actionable behavioral context.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is concise, with two short sentences that front-load the purpose and then provide practical guidance on URL selection. No wasted words or redundant fluff.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness5/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  For a simple single-parameter read-only tool, the description adequately covers return content, usage tip, and safety (via annotations). Although no output schema exists, the description highlights key response aspects like src sizes and courtesy credit, making it complete for the task.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  The input schema fully documents the single id parameter with type, bounds, and a clear description, so coverage is 100%. The description only restates 'numeric ID' and does not add new parameter semantics. The baseline of 3 applies due to complete schema coverage.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states the tool retrieves a single Pexels photo by its numeric ID, with specific return details (pre-sized URLs, courtesy credit). It is distinct from sibling search/curated/list tools, which focus on multiple results or collections.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines4/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description implies use when you already have a specific photo ID and need full details. It does not explicitly mention alternatives or when-not-to-use, but the singular 'get by ID' scope makes the context clear. Without explicit exclusions, it falls short of a 5.

  Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

• pexels_get_videoA
  4.3/5.0
  Behavior4/5

  Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

  Annotations already provide readOnlyHint and openWorldHint, and the description redundantly says 'Read-only.' However, it adds meaningful behavioral context beyond annotations: that the response includes every available rendition and the complete video_files list, not just a truncated subset. This is useful and not inferable from annotations.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  Two sentences, front-loaded with purpose and differentiator, and no wasted words. The read-only mention is redundant but short. Highly concise and well-structured.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness5/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  For a simple single-parameter get operation with no output schema, the description sufficiently covers the return behavior (full detail, complete video_files list), the key differentiator from siblings, and the read-only nature. Nothing critical is missing given the low complexity.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema coverage is 100% with the id parameter fully described as 'The numeric Pexels video ID.' The description reinforces this as 'numeric ID' but adds no new meaning beyond the schema. Baseline of 3 applies for high schema coverage.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states it gets a single Pexels video by numeric ID, and explicitly contrasts with search/popular tools by noting it returns the complete video_files list. This distinguishes it from siblings and clearly specifies the resource and scope.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines4/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  It indicates when to use this tool by contrasting with search/popular tools ('unlike the search/popular tools... returns the complete list'), implying use when a specific video ID is known and full detail is needed. It does not explicitly mention when not to use it or name sibling alternatives directly, but the differentiation is clear.

  Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

• pexels_list_my_collectionsA
  4.3/5.0
  Behavior4/5

  Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

  Annotations already declare readOnlyHint and openWorldHint, and the description adds meaningful behavioral context: the account-ownership semantics, the lack of per-conversation OAuth, and the possible empty result. It also explicitly states 'Read-only', reinforcing the annotation without contradicting it.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  Two sentences, front-loaded with the core purpose and pagination, followed by a necessary clarification about account ownership and emptiness. Every sentence earns its place; no wasted words.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness5/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  The tool is simple, has no output schema, and parameters are fully documented in the schema. The description fully covers the tool's context: account ownership, pagination, potential empty result, and read-only nature. Nothing critical is missing for an agent to select and invoke it correctly.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema coverage is 100% for both parameters, with descriptions for 'page' and 'per_page' already explaining their meaning and defaults. The description only adds the word 'paginated', which adds minimal value beyond the schema. Baseline 3 is appropriate.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description uses a specific verb ('List') and a specific resource ('collections belonging to the Pexels account that owns the configured API key'), clearly distinguishing it from siblings like pexels_list_featured_collections. It also adds pagination scope, making the purpose unambiguous.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines4/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description provides clear context: this tool reflects the API key's own account, not the chatting user, and may be empty without created collections. This implies when to use it (for personal collections) but does not explicitly name alternative tools or provide when-not-to-use exclusions.

  Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

• pexels_get_collection_mediaA
  4.4/5.0
  Behavior5/5

  Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

  Beyond the readOnlyHint annotation, the description discloses pagination, optional type filtering, compact shape with media_type tag, pre-sized URL options, and that video_files is trimmed while video_files_count gives the full count. This is valuable behavioral detail that cannot be inferred from annotations alone.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness4/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  Five sentences, each carrying substantive information. The first sentence front-loads the core purpose, and subsequent sentences add practical details about output shape and URL usage. It is somewhat dense but every sentence earns its place, with no repetition or filler.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness5/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  Given no output schema, the description thoroughly covers what the caller needs to know: return shape (compact, media_type-tagged), how to choose src URLs, video rendition trimming, and the alternative tool for full data. Pagination and filtering are mentioned, making it complete for a read-only list operation.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  The input schema is fully described (100% coverage), so the baseline is 3. The description adds a little by mentioning filtering to 'just photos or just videos' and the pagination nature, but it doesn't go beyond what the schema already states for each parameter.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description begins with a specific verb 'Get' and clearly identifies the resource: photos and/or videos inside a Pexels collection by its ID. This distinguishes it from sibling tools like search or list-collection tools, which focus on discovery or collection metadata.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines4/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description sets clear context for when to use this tool (when you have a collection ID and want its media) and explicitly directs users to pexels_get_video for complete rendition lists, demonstrating awareness of alternative tools. It doesn't enumerate exclusions (e.g., when not to use), but provides sufficient practical guidance.

  Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

• pexels_list_featured_collectionsA
  4.5/5.0
  Behavior4/5

  Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

  The annotations already declare readOnlyHint=true and openWorldHint=true, so read-only behavior is covered. The description adds value beyond annotations by stating it 'Returns collection metadata only' and is 'paginated', which are behavioral specifics not captured in the annotations. This is informative without being redundant.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is two sentences long, front-loaded with the core purpose, then includes an alternative, and ends with 'Read-only'. Every sentence adds essential information with zero fluff. It is concise and well-structured for quick scanning by an AI agent.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness5/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  Given the tool has only two optional parameters fully documented in the schema, no output schema, and annotations covering read-only and open-world hints, the description is complete. It states the resource (featured collections), the scope (metadata only), the pagination behavior, and the path to get media—addressing all likely follow-up needs without requiring extra inference.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  The schema fully describes both parameters (page and per_page) with clear descriptions and defaults (100% coverage). The description mentions 'paginated' but does not add any additional meaning to the parameters beyond what the schema provides. Baseline of 3 is appropriate since the schema carries the explanatory weight.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states the tool lists 'Pexels' featured collections' and specifies it is 'paginated'. It distinguishes from siblings by noting it returns 'collection metadata only', which separates it from pexels_get_collection_media and pexels_list_my_collections (featured vs. my). The verb 'list' makes the action unambiguous.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines5/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description provides an explicit alternative: 'call pexels_get_collection_media for the photos/videos inside one', telling users exactly when to use a different tool. It also implies this tool is for collection metadata rather than media, giving clear usage context. The 'Read-only' note further guides safe usage.

  Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

• pexels_search_videosA
  4.5/5.0
  Behavior5/5

  Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

  Beyond the readOnlyHint annotation, the description reveals important behavioral details: it returns compact video objects, trims video_files to highest-resolution renditions, and references video_files_count for the full count. It also directs users to pexels_get_video for complete data, which adds transparency about data limits not evident from annotations.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is two sentences, front-loaded with the core purpose, and each clause adds value: the filter list, return format, read-only note, and important trimming behavior. There is no wasted wording or duplication of schema details.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness5/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  With no output schema present, the description adequately explains what the tool returns (compact video objects with rendition links) and clarifies a critical data transformation (trimmed video_files). It also gives a cross-reference to pexels_get_video for complementary data, making the tool's behavior sufficiently complete for selection and invocation.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  The input schema already covers all six parameters with detailed descriptions (e.g., size enum, page defaults, locale examples), achieving 100% schema coverage. The description only summarizes these as 'optional orientation/size/locale filters' without adding new meanings; thus the baseline of 3 is appropriate since the schema does the heavy lifting.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states 'Search Pexels for videos matching a query' along with optional filters, making the tool's purpose specific and unambiguous. It distinguishes itself from sibling tools like pexels_search_photos by focusing on videos and from pexels_get_video by indicating it is a search operation.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines4/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description provides clear context for when to use this tool—when searching videos by query—and explicitly names pexels_get_video as the alternative for retrieving the complete rendition list for a single video. It does not explicitly exclude other search variants like pexels_popular_videos, but the query-based filtering makes the usage context clear.

  Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

• pexels_popular_videosA
  4.7/5.0
  Behavior5/5

  Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

  The description discloses that video_files are trimmed to highest-resolution renditions and mentions video_files_count, and notes 'Returns compact video objects' – adding behavioral context beyond the readOnlyHint annotation.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  Three sentences are packed with purpose, filters, response format, and an alternative tool reference; no filler words.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness5/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  Despite no output schema, the description explains response compactness, the trimming behavior, and where to get full renditions, covering the important behavioral aspects for a list tool.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Input schema covers 100% of parameters with descriptions; the description only groups them as 'minimum width/height and duration range' without adding new semantics, so baseline score of 3 applies.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description uses the specific verb 'List' with the resource 'currently popular Pexels videos' and further specifies optional filters, distinguishing it from sibling tools like search_videos and curated_photos.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines5/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  It explicitly directs users to call pexels_get_video when complete rendition lists are needed, and states the tool is read-only, providing clear guidance on when to use this tool versus an alternative.

  Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.